{"id":"https://openalex.org/W7118363077","doi":"https://doi.org/10.3390/jimaging12010030","title":"From Visual to Multimodal: Systematic Ablation of Encoders and Fusion Strategies in Animal Identification","display_name":"From Visual to Multimodal: Systematic Ablation of Encoders and Fusion Strategies in Animal Identification","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7118363077","doi":"https://doi.org/10.3390/jimaging12010030","pmid":"https://pubmed.ncbi.nlm.nih.gov/41590916"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging12010030","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12010030","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/jimaging12010030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114316561","display_name":"Vasiliy Kudryavtsev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110898","display_name":"Moscow Technical University of Communication and Informatics","ror":"https://ror.org/015zw2f19","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210110898"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Vasiliy Kudryavtsev","raw_affiliation_strings":["Faculty of IT, Technical University of Communication and Informatics, Moscow 111024, Russia"],"raw_orcid":"https://orcid.org/0009-0001-9935-7514","affiliations":[{"raw_affiliation_string":"Faculty of IT, Technical University of Communication and Informatics, Moscow 111024, Russia","institution_ids":["https://openalex.org/I4210110898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114316560","display_name":"Kirill Borodin","orcid":"https://orcid.org/0009-0001-8203-1059"},"institutions":[{"id":"https://openalex.org/I4210110898","display_name":"Moscow Technical University of Communication and Informatics","ror":"https://ror.org/015zw2f19","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210110898"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Kirill Borodin","raw_affiliation_strings":["Faculty of IT, Technical University of Communication and Informatics, Moscow 111024, Russia"],"raw_orcid":"https://orcid.org/0009-0001-8203-1059","affiliations":[{"raw_affiliation_string":"Faculty of IT, Technical University of Communication and Informatics, Moscow 111024, Russia","institution_ids":["https://openalex.org/I4210110898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122296229","display_name":"German Berezin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110898","display_name":"Moscow Technical University of Communication and Informatics","ror":"https://ror.org/015zw2f19","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210110898"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"German Berezin","raw_affiliation_strings":["Faculty of IT, Technical University of Communication and Informatics, Moscow 111024, Russia"],"raw_orcid":"https://orcid.org/0009-0006-9791-5216","affiliations":[{"raw_affiliation_string":"Faculty of IT, Technical University of Communication and Informatics, Moscow 111024, Russia","institution_ids":["https://openalex.org/I4210110898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069603544","display_name":"Kirill Bubenchikov","orcid":null},"institutions":[{"id":"https://openalex.org/I45571689","display_name":"Moscow Aviation Institute","ror":"https://ror.org/033zpbv42","country_code":"RU","type":"education","lineage":["https://openalex.org/I45571689"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Kirill Bubenchikov","raw_affiliation_strings":["AI Lab, Avito, Moscow 125196, Russia"],"raw_orcid":"https://orcid.org/0009-0005-3847-5719","affiliations":[{"raw_affiliation_string":"AI Lab, Avito, Moscow 125196, Russia","institution_ids":["https://openalex.org/I45571689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041288941","display_name":"Grach Mkrtchian","orcid":"https://orcid.org/0000-0002-5802-5513"},"institutions":[{"id":"https://openalex.org/I4210110898","display_name":"Moscow Technical University of Communication and Informatics","ror":"https://ror.org/015zw2f19","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210110898"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Grach Mkrtchian","raw_affiliation_strings":["Faculty of IT, Technical University of Communication and Informatics, Moscow 111024, Russia"],"raw_orcid":"https://orcid.org/0000-0002-5802-5513","affiliations":[{"raw_affiliation_string":"Faculty of IT, Technical University of Communication and Informatics, Moscow 111024, Russia","institution_ids":["https://openalex.org/I4210110898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060069695","display_name":"Alexander Ryzhkov","orcid":null},"institutions":[{"id":"https://openalex.org/I45571689","display_name":"Moscow Aviation Institute","ror":"https://ror.org/033zpbv42","country_code":"RU","type":"education","lineage":["https://openalex.org/I45571689"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexander Ryzhkov","raw_affiliation_strings":["AI Lab, Avito, Moscow 125196, Russia"],"raw_orcid":"https://orcid.org/0009-0008-5422-1649","affiliations":[{"raw_affiliation_string":"AI Lab, Avito, Moscow 125196, Russia","institution_ids":["https://openalex.org/I45571689"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114316561"],"corresponding_institution_ids":["https://openalex.org/I4210110898"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02474004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"1","first_page":"30","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11214","display_name":"Human-Animal Interaction Studies","score":0.33869999647140503,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11214","display_name":"Human-Animal Interaction Studies","score":0.33869999647140503,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12486","display_name":"Food Supply Chain Traceability","score":0.08460000157356262,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.04520000144839287,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7610999941825867},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5764999985694885},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4925000071525574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4853000044822693},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.44929999113082886},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.41530001163482666},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.39739999175071716},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3944000005722046},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.38179999589920044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312000036239624},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7610999941825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6759999990463257},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5764999985694885},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39070001244544983},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.38179999589920044},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.2660999894142151}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/jimaging12010030","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12010030","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:41590916","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41590916","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":null},{"id":"pmh:oai:arXiv.org:2603.02270","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.02270","pdf_url":"https://arxiv.org/pdf/2603.02270","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:535fb5143d91440d9f5d08e6cffecbd2","is_oa":true,"landing_page_url":"https://doaj.org/article/535fb5143d91440d9f5d08e6cffecbd2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 12, Iss 1, p 30 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12843040","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12843040/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/jimaging12010030","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12010030","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automated":[0],"animal":[1],"identification":[2],"is":[3],"a":[4,33,52,109,115,128],"practical":[5],"task":[6],"for":[7,101],"reuniting":[8],"lost":[9],"pets":[10],"with":[11,41],"their":[12],"owners,":[13],"yet":[14],"current":[15],"systems":[16],"often":[17],"struggle":[18],"due":[19],"to":[20,64,93,96],"limited":[21],"dataset":[22],"scale":[23],"and":[24,75,81,113,120,142],"reliance":[25],"on":[26,127],"unimodal":[27,140],"visual":[28,39],"cues.":[29],"This":[30],"study":[31],"introduces":[32],"multimodal":[34],"verification":[35],"framework":[36],"that":[37,144],"enhances":[38],"features":[40],"semantic":[42,147],"identity":[43],"priors":[44],"derived":[45],"from":[46,90],"synthetic":[47],"textual":[48],"descriptions.":[49],"We":[50,84],"constructed":[51],"massive":[53],"training":[54],"corpus":[55],"of":[56,118,125],"1.9":[57],"million":[58],"photographs":[59],"covering":[60],"695,091":[61],"unique":[62],"animals":[63],"support":[65],"this":[66],"investigation.":[67],"Through":[68],"systematic":[69],"ablation":[70],"studies,":[71],"we":[72],"identified":[73],"SigLIP2-Giant":[74],"E5-Small-v2":[76],"as":[77],"the":[78,98],"optimal":[79],"vision":[80],"text":[82],"backbones.":[83],"further":[85],"evaluated":[86],"fusion":[87,111],"strategies":[88],"ranging":[89],"simple":[91],"concatenation":[92],"adaptive":[94],"gating":[95],"determine":[97],"best":[99],"method":[100],"integrating":[102,145],"these":[103],"modalities.":[104],"Our":[105],"proposed":[106],"approach":[107],"utilizes":[108],"gated":[110],"mechanism":[112],"achieved":[114],"Top-1":[116],"accuracy":[117],"84.28%":[119],"an":[121,135],"Equal":[122],"Error":[123],"Rate":[124],"0.0422":[126],"comprehensive":[129],"test":[130],"protocol.":[131],"These":[132],"results":[133],"represent":[134],"11%":[136],"improvement":[137],"over":[138],"leading":[139],"baselines":[141],"demonstrate":[143],"synthesized":[146],"descriptions":[148],"significantly":[149],"refines":[150],"decision":[151],"boundaries":[152],"in":[153],"large-scale":[154],"pet":[155],"re-identification.":[156]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-08T00:00:00"}